Model comparison
Grok 4.6 vs Inkling-Small
Grok 4.6 is the stronger model overall, scoring 56.9 to 46.5 on the Noometry Index. Inkling-Small costs 4.7× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Last verified . 32 shared benchmarks.
Summary
- They share 32 benchmarks with published results for both. Grok 4.6 scores higher in 9 categories and Inkling-Small in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.6 leads 61.4 to 38.6.
- The biggest single-benchmark swing is ProofBench: 51% for Grok 4.6 and 6% for Inkling-Small.
- Inkling-Small is cheaper at $0.45 / $1.20 per million input/output tokens, against $2 / $6 for Grok 4.6.
- Inkling-Small accepts more context: 524K tokens versus 500K.
- Inkling-Small has downloadable open weights; the other is API-only.
Side by side
| Grok 4.6 | Inkling-Small | |
|---|---|---|
| Provider | xAI | Thinking Machines Lab |
| Noometry Index | 56.9 | 46.5 |
| Released | 2026-08-12 | 2026-07-15 |
| Weights | Proprietary | Open |
| Context window | 500K | 524K |
| Max output | 500K | 1.05M |
| Input $ / M tokens | $2 | $0.45 |
| Output $ / M tokens | $6 | $1.20 |
| Results tracked | 49 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.6 leads
Grok 4.6: 58.5 (#16), Inkling-Small: 43.6 (#85)
| Benchmark | Grok 4.6 | Inkling-Small |
|---|---|---|
| LMArena WebDev | 1617 | 1409 |
| SciCode | 56.5% | 48.7% |
| LMArena Coding | 1465 | 1451 |
| DeepSWE | 67.5% | — |
| FrontierCode | 48% | — |
| CursorBench | 41.4% | — |
| FrontierSWE | 25.3% | — |
| WeirdML | 67.3% | — |
| ALE-Bench | 1,508 | — |
Agentic & Tool Use Not comparable
Grok 4.6: 39.4 (#27), Inkling-Small: —
| Benchmark | Grok 4.6 | Inkling-Small |
|---|---|---|
| APEX-Agents | 65.3% | — |
| GDP.pdf | 17.2% | — |
| Vending-Bench 2 | 9,047 | — |
Reasoning Grok 4.6 leads
Grok 4.6: 61.4 (#20), Inkling-Small: 38.6 (#63)
| Benchmark | Grok 4.6 | Inkling-Small |
|---|---|---|
| ARC-AGI-2 | 67.1% | 40.1% |
| ARC-AGI-1 | 87.5% | 84% |
| CritPt | 19.7% | 8.3% |
| Chess Puzzles | 40% | 18% |
| LMArena Hard Prompts | 1447 | 1423 |
| Mystery Game Puzzles | 34% | 6% |
| Epoch Capabilities Index | 156.44 | 150.15 |
| SimpleBench | 75.9% | — |
| NYT Connections (extended) | 80% | — |
| EBR-Bench | 30.5% | — |
| DTBench | 97.3% | — |
| LMCA | 48.5% | — |
Math Grok 4.6 leads
Grok 4.6: 67.0 (#24), Inkling-Small: 45.1 (#77)
| Benchmark | Grok 4.6 | Inkling-Small |
|---|---|---|
| FrontierMath (Tiers 1-3) | 66% | 46.3% |
| FrontierMath Tier 4 | 31.7% | 17.1% |
| OTIS Mock AIME 2024-2025 | 99.2% | 90% |
| ProofBench | 51% | 6% |
| LMArena Math | 1423 | 1459 |
Knowledge Grok 4.6 leads
Grok 4.6: 63.3 (#20), Inkling-Small: 48.2 (#77)
| Benchmark | Grok 4.6 | Inkling-Small |
|---|---|---|
| GPQA Diamond | 94% | 88.5% |
| SimpleQA Verified | 49.3% | 19.1% |
| LMArena Expert | 1467 | 1442 |
Multimodal Grok 4.6 leads
Grok 4.6: 43.6 (#23), Inkling-Small: 39.1 (#62)
| Benchmark | Grok 4.6 | Inkling-Small |
|---|---|---|
| LMArena Vision | 1263 | 1235 |
| Blueprint-Bench 2 | 33.2% | — |
| Furniture Assembly | 40% | — |
| LMArena Document | 1452 | — |
Multilingual Grok 4.6 leads
Grok 4.6: 53.0 (#74), Inkling-Small: 51.7 (#104)
| Benchmark | Grok 4.6 | Inkling-Small |
|---|---|---|
| LMArena Non-English | 1420 | 1402 |
| LMArena Chinese | 1480 | 1465 |
| LMArena French | 1461 | 1436 |
| LMArena German | 1431 | 1405 |
| LMArena Japanese | 1376 | 1405 |
| LMArena Korean | 1397 | 1363 |
| LMArena Russian | 1422 | 1391 |
| LMArena Spanish | 1404 | 1428 |
Instruction Following Grok 4.6 leads
Grok 4.6: 75.4 (#63), Inkling-Small: 73.8 (#114)
| Benchmark | Grok 4.6 | Inkling-Small |
|---|---|---|
| LMArena Instruction Following | 1431 | 1399 |
Long Context Grok 4.6 leads
Grok 4.6: 44.5 (#66), Inkling-Small: 42.7 (#118)
| Benchmark | Grok 4.6 | Inkling-Small |
|---|---|---|
| LMArena Longer Query | 1454 | 1401 |
Writing & Preference Grok 4.6 leads
Grok 4.6: 62.3 (#80), Inkling-Small: 59.6 (#107)
| Benchmark | Grok 4.6 | Inkling-Small |
|---|---|---|
| LMArena Text | 1428 | 1414 |
| LMArena Creative Writing | 1428 | 1331 |
| LMArena Multi-Turn | 1425 | 1418 |
| EQ-Bench Creative Writing | — | 1491 |
Frequently asked questions
Is Grok 4.6 better than Inkling-Small?
Grok 4.6 is the stronger model overall, scoring 56.9 to 46.5 on the Noometry Index. Inkling-Small costs 4.7× less per token, which makes it the better buy when Grok 4.6's lead doesn't matter for your workload.
Which is cheaper, Grok 4.6 or Inkling-Small?
Inkling-Small is cheaper. It lists at $0.45 per million input tokens and $1.20 per million output tokens; Grok 4.6 lists at $2 and $6.
Is Grok 4.6 or Inkling-Small better for coding?
Grok 4.6 scores higher on coding benchmarks: 58.5 versus 43.6 in the Noometry coding category.
Which has the bigger context window?
Inkling-Small does, with 524K tokens against 500K.
How many benchmarks do Grok 4.6 and Inkling-Small share?
32 benchmarks have published results for both models. Grok 4.6 has 49 scored results on Noometry and Inkling-Small has 33.